Search

This research analyses ventricular arrhythmias caused by Ca2+, Na+, and K+ ion channel dysfunction. Most arrhythmias are caused by cardiac myocardial Action Potential (AP) production or conduction. Humans cardiac cell based on Ten Tusscher's endocardial cell model. The TT model data is updated based on Han's experimental data to describe human ventricular cell Ca2+, Na+, K+ levels and channel kinetics. The individual's ventricle simulation is analysed using Euler integration for various channel failure circumstances in 50 samples. Sample size was determined using criterion 0.05, G Factor 80%, interval of confidence 95%, and enrolment ratio 1. An insignificant difference was seen between normal and atypical arrhythmias (p<0.001). The extracellular Calcium Occupancy (Ca2+o) is 2mM, with AP mean values from +15mV to -85mV. Abnormal concentrations like (100%=4mM) have AP mean values from 35mV to -70mV. The exogenous Na+ Oxidation (Na+o) value is 140mM, with AP mean values of +20mV to -105mV, whereas abnormal levels such (100%=280mM) with AP mean values of 18mV to -70mV. The exogenous K+ Oxidation (K+o) value is 5.4mM, with AP mean values of +18mV to - 95mV, whereas abnormal levels such (100%=10.8mM) with AP mean values of 10mV to -75mV. Cardiac myocyte Na+, K+, and Ca2+ concentrations tightly govern the AP, yet they change continuously due to typical bodily control of cardiac electricity, flexible, and metabolic conditions. Repolarization happens and peak periods are caused by K+ and Ca2+ levels, whereas depolarization is caused by Na+ ions. [ABSTRACT FROM AUTHOR]

One of the leading causes of death is cardiovascular disease (CVD). This disease is the cause of 31% of deaths worldwide in 2016, and 85% of them are heart attacks. The traditional way to detect CVD is based on medical records and clinical analysis of the patient. Electrocardiogram (ECG) analysis is one way to determine irregular heartbeat or arrhythmia. Computer assistance with implementing specific machine learning algorithms can help recognize irregular heartbeats automatically. However, raw ECG data may contain noise that affects the accuracy of irregular heartbeat detection. In this study, the ECG data used was from the Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) database. The data has four categories: Normal, Atrial Fibrillation, PVC Bigeminy, and Ventricular Tachycardia. ECG raw data processing using multilevel discrete wavelet transforms (DWT) based on Haar and Daubechies wavelet. The process uses various values of mode (i.e. db1 until db10), level (i.e. level 1 and level 2), and filter (low and high pass filter), and the result is 20 data processed. Each data is used to create a model with several classification algorithms, i.e. K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Naïve Bayes, Decision Tree, Random Forest, and Deep Forest. The validation process uses 10-fold cross-validation. The results of this study indicate that Multilevel Discrete Wavelet Transforms improve irregular heartbeat detection accuracy when compared to raw ECG and processed data using a single DWT. While the best detection accuracy is the Deep Forest model, with an accuracy value of 63.57% using processed data with db1 mode values, level 2 and combining high and low pass filters. [ABSTRACT FROM AUTHOR]

The primary purpose of this research is to use the Support Vector Machine (SVM) classifier and the Naive Bayes (NB) classifier to make arrhythmia predictions from the MIT-BIH database. With an alpha of 0.05, 95% confidence interval (CI), 80% power, and an enrollment ratio of 1, the proposed research employed SVM and NB machine learning algorithms to predict arrhythmia using the MIT-BIH dataset of 65 normal and 65 abnormal ECG signals downloaded from IEEE dataport in.xlsx format. We used the data mining programme WEKA 3.8.5 to determine how to categorise people with and without arrhythmia. IBM SPSS version 21 was used for the statistical analysis. When comparing SVM and NB classifiers, a statistically significant difference (p0.010) was found. Using WEKA's 10-fold cross-validation for training and testing, the SVM classifier outperformed the NB classifier with an 88.50% accuracy rate in classification (80.39 percent). [ABSTRACT FROM AUTHOR]

The primary goal of this research is to use J48 and K-Nearest Neighbor (KNN) classifiers to predict arrhythmia using the MIT-BIH database. With an alpha of 0.05, 95% confidence interval (CI), 80% power, and an enrollment ratio of 1, the proposed study used the J48 and KNN machine learning algorithms to predict arrhythmia using data from the MIT-BIH dataset consisting of healthy (n=65) and arrhythmia (n=65) ECG signals collected from IEEE dataport in.XLSX format. WEKA 3.8.5, a data mining tool, was used to distinguish between those with arrhythmia and those without. IBM SPSS version 21 was used for the statistical analysis. There was no discernible difference (p=0.025) between the J48 and KNN classifiers. Using WEKA's 10-fold cross validation to train, test, and verify the classifiers, we find that the J48 classifier is more accurate at classifying data (89.80 percent) than the KNN classifier (87.64 percent). [ABSTRACT FROM AUTHOR]

Aim: To investigate the sodium atom movie potential to divert impacts in atrial center Electrocardiogram (ECG) age for the norm and remarkable condition utilizing Rungekutta system. Materials and Methods: In this research human atrial cells are based on Seemann et al. method can be used to describe the action potential model of sinoatrial nodes. Sample size can be calculated as 70 and the G power is 80%. Results: The conventional film capacity of sodium is 81.2 mV, but for the different abnormal values of 100%, half and 25%, then the membrane potentials are 162.4 mV, 121.8 mV and 101.5 mV and thereafter the reducing of 100% sodium levels doesn't outline single ECG waveform, decreasing of half and 25%, the membrane potentials are 40 mV and 37.7 mV. By taking a gander at these characteristics there is a differentiation in pacemaking development and causes capricious heart beat and prolongation occurs. Conclusion: In common place Action Potential, the withdrawal will happen reliably. In strange AP, the conduction of electrical excitation will change and make erratic heart work cause arrhythmia. A predominant perception of the cell model can be used to perceive the prescription that helps with making a regular heart beat. [ABSTRACT FROM AUTHOR]

The relationship between purkinje fibre cells (PFC) and ventricular myocardium is the focus of this investigation. Ca2+ concentration mediates AP production under these conditions. Our theoretical framework is based on Aslandi's (2001) humanendocardial cell model (ALD). The ALD model is improved by the experimental data provided by Han on human PFC Ca2+ currents. While keeping the same threshold (0.05), G power (80%), confidence interval (95%) and enrollment ratio, we apply the Euler integration method to the same 100 data from the human PFC model and analyse it under various concentration failure scenarios (1:1). While the action potential (AP) is at -53.04 mV when exposed to 2 mM external Ca2+, it falls with increasing concentrations of Ca2+o in the prefrontal cortex (10%=2.2 mM, 25%=2.5 mM, 50%=3 mM, and 100%=4 mM). Ca2+o at 10% in the PFC is equivalent to 1.8 mM, 25% to 1.5 mM, 50% to 1 mM, and 100% to 0.1 mM, with corresponding AP values of -42.76, -53.89, -55.08, and -45.88 mV. AP for raising PFC Ca2+i by 10% (=1.1 mM), 25% (=1.25 mM), 50% (=1.5 mM), and 100% (=2 mM), and AP for lowering PFC Ca2+i by 10% (=-54.64 mV), 25% (=-50.38 mV), 50% (=-53.04 mV), and 100% (=-0.32 mV). When comparing healthy and diseased states, a wide range of values for the average L-type Ca2+ current (ICaL, measured in Pico Amperes [pA]) is seen. Normal and abnormal Ca2+ concentrations in intracellular and extracellular PFC modify the plateau phase, and longer-than-usual AP cycles are associated with heart failure. [ABSTRACT FROM AUTHOR]

Automated diagnosis of the cardiovascular disease from heartbeats of an individual is a difficult and challenging task. Essentially, it requires continuous monitoring system to track the irregular heartbeats in order to reduce the fatality rates. Electrocardiogram (ECG) is considered as one of the cheapest and most efficient clinical record used in hospitals to examine the cardiovascular condition of a heart patient. It is treated as a benchmark for sensing and identifying irregular heart rhythms. In modern era, due to abrupt increase in number of heart patients, cardiovascular health has become more important. In this paper, the aim of the research is to classify and predict the abnormal heartbeats from five different pre-defined classes such as, 'Fusion of Ventricular and Normal Beat', 'Supraventricular Premature Beat', 'Normal', 'Premature Ventricular Contraction' and 'Unclassifiable Beat'. The pre-trained VGG19 and DenseNet201 deep transferred learning models is used for classification and prediction. The proposed method is able to achieve overall 98% and 99% accuracy for VGG19 and DenseNet201 models, respectively. [ABSTRACT FROM AUTHOR]

The electrocardiogram (ECG) shows the plot of the bio-potential produced by the movement of the heart and is utilized by doctors to foresee and treat different cardiovascular illnesses. The arrangement of electrocardiogram (ECG) signals assumes a significant function in the conclusions of heart illnesses. An exact ECG grouping is a difficult issue. Early and precise discovery of arrhythmia, Congestive Cardiovascular breakdown types is significant in distinguishing heart infections and picking suitab le treatment for a patient. Various classifiers are accessible for ECG orders. Among all classifiers, Convolution Neural Organizations (CNNs) like ALEXNET have become exceptionally famous and most broadly utilized for ECG grouping. This paper examined the issues engaged with ECG order and presents a definite studyof pre-handling strategies, ECG information bases, highlight extraction methods, CNN-based classifiers, and execution measures to address the referenced issues using the IoT-based mechanisms. [ABSTRACT FROM AUTHOR]

Atrial fibrillation (AF) is a commonly observed cardiac arrhythmia in clinical contexts, accounting for roughly one-third of hospitalizations for cardiac rhythm disorders. The present epidemiological evidence has substantiated that Atrial Fibrillation (AF) is a prevalent worldwide epidemic that has deleterious effects on both enduring morbidity and mortality. The manual interpretation of an electrocardiogram (ECG) for diagnostic purposes is a demanding and time-consuming process that requires a significant level of expertise. Furthermore, the issue is characterized by inconsistencies among various observers and even within a single observer. The identification of Atrial Fibrillation (AF) presents difficulty owing to its frequent asymptomatic nature and the necessity of conducting multiple diagnostic examinations to verify its existence. The lack of adequate documentation or identification of atrial fibrillation (AF) and its associated comorbidities is a cause for concern. Atrial fibrillation (AF) has the capacity to give rise to significant medical complications, such as stroke and heart failure, among others. The proposed study aims to create a machine learning algorithm that has low computational requirements and can accurately identify Atrial fibrillation in its early stages using short single lead electrocardiogram signals in near real-time. The framework under consideration has been primarily developed with a focus on the Heart Rate Variability (HRV) characteristics of the human cardiac cycle. The framework underwent training and testing on the MIT-BIH Atrial Fibrillation and CinC 2017 Database and demonstrated a sensitivity of 95.30% and specificity of 94.71% through the implementation of a ten-fold cross-validation approach. The framework was subjected to experimentation using medical samples obtained from a local laboratory, and the results indicate an accuracy rate of approximately 91.5%. The proposed method could help doctors find atrial fibrillation early on during routine ECG screenings. [ABSTRACT FROM AUTHOR]

One of the most common and practical tools for predicting and diagnosing cardiac problems is the electrocardiogram (ECG) signal. It is an advanced medical device fundamental that monitors track of cardiac excitability, transmission, and recovery. It Provides essential information on the functional features of the heart and cardiovascular system. In this work, a technique for classifying an ECG image of a patient case into four classes is proposed. This class includes (MI, Arrhythmia, History MI, and Normal case). There are three steps to the proposed system: The procedure includes "image pre-processing, feature extraction, and classification". In order to prepare and enhance the input images, certain image preprocessing techniques are utilized in the early step. Color images are converted to binary images. Utilizing local binary pattern modulation, features are extracted from the images in the second step (LBP). The extracted features are sent into a 1D ML algorithm as input in the third step. Three ML algorithms are utilized. For ECG classification, these algorithms are "K-Nearest Neighbors (KNN), Random Forest (RF), and Logistic Regression (LR)." Algorithms achieved successful results during the ECG classification process, The findings show that the suggested technique is excellent in RF the range of this classification precision is 93.66 percent, and very good in K-NN the range of this classification precision is 80.53 percent, and good degree in LR the range of this classification precision is 70.87 percent. As evidenced by the low number of fault alarms and high accuracy rate, the suggested system performs exceptionally well in classifying ECG images. [ABSTRACT FROM AUTHOR]

Time series classification (TSC) has an important role in medical diagnostics, providing decision support for vector-shaped data received from biomedical sensors. Traditional machine learning methods provide a sufficient baseline, while they need additional feature extraction procedures and result in lower accuracy compared to recent deep learning approaches. Providing more reliable results, deep learning architectures have become the golden standard for TSC tasks, evoking studies about which architecture provides better results with faster implementation. This study aims to provide a comparison between well-known deep learning architectures CNN and LSTM in comparison with traditional ANN, applying these classifiers for the MIT/BIH Arrhythmia Database, an Electrocardiogram (ECG) dataset that is publicly available. Results show that the best accuracy is achieved for CNN architecture used (96.17%), while LSTM resulted in comparable accuracy (94.42%) and traditional ANN (88.98%) could not compete with the more recent and complicated architectures. These outcomes indicate that although vector-shaped signals have relatively lower complexity compared to two or more-dimensional data like images, more complicated deep learning architectures outperform the traditional neural networks indicating exploration of high order patterns in one dimensional data improves classification accuracy. [ABSTRACT FROM AUTHOR]

Heart Failure (HF) is one of the major causes in today's industrial world. In that arrhythmias (abnormal electrical activity) is one, which is responsible for generating life threatening arrhythmias like ventricular tachycardia and fibrillation. In this article, analyse the Sodium (Na+) ion concentration effects in ventricular cells for normal and arrhythmic conditions using a computational approach. Ten Tusscher's (TT) model of the human endocardial cell was used to generate single Action Potential (AP) based on Han's experimental data. In that we modified the data to describe the properties of Na+transient process currents and their channel dynamics in TT models. Different channel failure conditions in the same group (n=50) samples of TT models are used to analyse by using the Euler integration method. The normal intracellular Na+ concentration (Na+i) value is 11.6mM, which having AP mean values in the range of +20millivolt (mV) to -105mV but for different abnormal such as (10%=12.76mM, 25%=14.5mM, 50%=17.4mM, 100%=23.2mM) having AP of mean values like (10%=10mV to -90mV, 25%=5mV to -95mV, 50%=-5mV to -98mV, 100%=-40mV to -105mV) Similarly, extracellular Na+ Concentration (Na+) value is 140mM, which having AP mean values in the range of +20millivolt to -105millivolt but for different abnormal such as (10%=154mM, 25%=175mM, 50%=230mM, 100%=280mM) having AP of mean values like (10%=12mV to -80mV, 25%=14mV to -75mV, 50%=15mV to -72mV, 100%=18mV to -70mV). It was observed that there was an insignificant difference between normal and abnormal arrhythmias conditions (p<0.001). Abnormal Na+ Concentration in intracellular and extracellular at Cardiac myocyte as a result of disturbing the natural physiological regulation of cardiac electrical, contractile, and energetic states. [ABSTRACT FROM AUTHOR]

The aim of this study is to analyze synchronisation and coordination of purkinje fibre cells (PFC) with ventricular myocardium. In that particular focus on Sodium (Na+) concentration is responsible for Action potential (AP) generation. Here this paper is based on the model of Humanendocardial cell by Aslandi (ALD). The ALD model data is modified based on the experimental data of Han, describing the properties of Na+ currents in human PFC. Euler integration protocol is used to analyze the human PFC model for different concentration failure conditions in the same group of 100 samples by keeping threshold 0.05, G power 80%, confidence interval 95% and enrolment ratio 1. The normal AP is -53.04 mV for normal Extracellular Na+ Concentration (Na+o =140mM) and for different increasing levels of Na+o in PFC like (10%=154mM, 25%=175mM, 50%=210mM, 100%=280mM) having AP as (10%= -52.56mV, 25%= -56.26mV, 50%= -44.56mV, 100%= -39.39mV). AP for different decreasing levels of Na+o in PFC like (10%= 126mM, 25%=105mM, 50%=70mM, 100%=0.1mM) having (10%= -51.98mV, 25%= -72.02mV, 50%= -75.75mV, 100%= -75.35mV). AP for different increasing level of intracellular Na+ concentration (Na+i)in PFC like (10%=8.8mM, 25%=10mM, 50%=12mM, 100%=16mM) having AP (10%=-53.08mV, 25%=-70.58mV, 50%=-73.47mV, 100%=-76.76mV), AP for different decreasing levels of Na+i in PFC like (10%=7.2mM, 25%=6mM, 50%=4mM, 100%=0.1mM) having (10%=-46.46mV, 25%=34.92mV, 50%=-28.98mV, 100%= -25.14mV). Similarly its mean value of fast Na current (INa in Pico Ampere (pA)) varied according to different deviant conditions. The results of normal and abnormal concentration of Na+ in intracellular and extracellular PFC affects the depolarization phase due to prolonged total cycle length of AP which leads to cardiac failure. [ABSTRACT FROM AUTHOR]

To investigate the calcium particle membrane potential to divert impacts in atrial node Electrocardiogram (ECG) age for the ordinary and unusual condition utilizing Rungekutta technique. In this research human atrial cells are based on [1] method can be used to describe the action potential model of sinoatrial nodes. Sample size can be calculated as 70 and the G power is 80%. The normal membrane potential of calcium is -30 mV, but for the different abnormal values that is increasing of 100%, 50% and 25% of the membrane potentials are -52mV, -26mV and -42mV and then the decreasing of 100% and 50% calcium levels does not form single ECG waveform, decreasing of 25%, the membrane potential is - 45mV which having the mean value range of 7mV to 17mV. By comparing these values there is a difference in peacemaking activity and causes irregular heart beat and prolongation occurs. In normal Action potential, the contraction will occur regularly. In abnormal AP, the conduction of electrical excitation will differ and make irregular heart function cause arrhythmia. In the future, a better understanding of the cellular model can be used to detect the drug that helps to make a normal heart beat. [ABSTRACT FROM AUTHOR]

The main purpose of the study is to predict arrhythmia from the MIT-BIH database using Random Forest (RF) and Voted Perceptron (VP) classifiers. Materials and Methods: The proposed study uses the RF and VP Machine learning Algorithms to predict the arrhythmia using MIT-BIH dataset with healthy (n=65) and Arrhythmia (n=65) ECG signals collected from IEEE data port in.XLSX format for our study with alpha value as 0.05, 95% as CI, power as 80% and enrolment ratio as 1. The classification of arrhythmia and healthy subjects was performed using WEKA 3.8.5, a data mining tool. The statistical analysis was performed on IBM SPSS software version 21. RESULTS: The statistical significant difference (p<.000) was observed between RF and VP classifiers. Conclusion: The classifiers have been trained, tested, validated using 10 fold cross-validation in WEKA software, the innovative voted perceptron classifier has achieved a higher classification accuracy rate (88.86)% than RF classifier (87.06)%. [ABSTRACT FROM AUTHOR]

The majority of heart illnesses can be diagnosed by analysing the ECG signal for arrhythmias. The P-QRS-T waves in an ECG signal represent one cardiac cycle. Due to varied aberrant rhythms and noise distribution, extracting powerful features from raw ECG data for fine-grained illnesses classification remains a difficult task today [1]. Previous research has primarily relied on heartbeat or single scale signal segments for ECG interpretation, ignoring the underlying complementing information of several scales. This suggested study addresses several methods and transformations that have been previously described in the literature for analysing an ECG signal and extracting features from an arrhythmia analysis. [ABSTRACT FROM AUTHOR]

This paper presents an advanced diagnostic strategy for identifying heart arrhythmia pathologies. The proposed approach utilizes ECG signal measurements taken over a 30-second interval and extracts statistical features from the RR intervals time series. A clustering scheme based on heart rate ranges is employed, and a mixture of experts with four sub-models is constructed, each assigned to a specific heart rate range. Additionally, a set of 25 geometric features derived from RR intervals and its derivatives is utilized. Through a statistical feature selection approach, irrelevant and uninformative features are eliminated, resulting in a subset of the most suitable features. The model setup is optimized using a heuristic optimization strategy to select the best sub-model for each cluster. The proposed approach achieves high performance with an average sensitivity of 98.77% and specificity of 98.78%, highlighting its potential as a valuable decision-making support tool for physicians. [ABSTRACT FROM AUTHOR]

Heartbeat is visualized as a series of electrical waves on the display. ECG signal conveys information about structure and functions of heart. To check the heart's electrical activity and rhythm a test called Electrocardiogram (ECG) is used An ECG helps to analyze symptoms of heart problems such as chest pain, Arrhythmias, shortness of breath, Coronary Artery Diseases, Heart Attacks etc. Artifacts and noises may get added to the signals and leads to a wrong diagnosis. Therefore, it is necessary to remove these noises to get proper diagnosis. ECG signals are low frequency signals in the range of 0.5Hz-100Hz. This paper discusses various ECG denoising techniques and also compares existing signal processing Algorithms for Denoising of ECG Signal Using Deep Learning. [ABSTRACT FROM AUTHOR]

Healthcare industry is in demand to adopt the new technologies that are in the market to improve their service quality. The telecommunication system is integrated with computing, Inter-networking, mobility, data storage, data analytics IoT (Internet of Things) centred technology is the order of the day. In this research work, our objective is to develop software that integrates the cloud computing and mobile technology for health care monitoring system. In present research, the stable fractal values are extracted from the ECG signals using Higuchi's method, which was not attempted by any researcher in the field of developing a computer aided diagnosis system for arrhythmia. From the results, the maximum classification accuracy for fractal features has been registered by support vector machine. 92.08% and 90.36%. The comparative evaluation was performed on 1) cloud -two node cluster 2) cloud-Ten node cluster. We presented software that integrates mobile computing and cloud computing for analyzing the ECG arrhythmia for five different arrhythmia classes. a) Class N b) Class S c) Class V d) Class F e) Class Q. This work proposed to evaluate cloud based architecture 1) cloud -two node cluster 2) cloud-Ten node cluster. Where the multi nodes cluster computing reduces the execution to almost to 50 per cent and maintains the response time. Dynamic resource allocation frame work has ability to distribute the load and maintain the time response. [ABSTRACT FROM AUTHOR]

The goal of this study is to create a new gadget that will be a breakthrough in medical technology by employing a high-precision error-correcting mechanism. This strategy is used to take advantage the device's ECG great accuracy. A portable device that already exists is compared to the newly invented gadget. This study proposes a portable gadget that is produced as a result of the Arduino software's mistake correcting. We can make do with a low-cost AD8232 sensor. Three locations on the electrode patch single lead sensor AD823 create the Einthoven triangle. The AD8232 sensor is the key component that processes the voltage received from the electrodes attached to the body to listen to the pulse. The text of the paper shows how to use the AD8232 sensor to collect ECG signals and connect them to an Arduino Uno. The Arduino serves as a sampler as well as an A/D converter (ADC). Once the sensor is connected to the Arduino, the electrodes are attached to the sensor and then to the patient's body to collect samples. The information is compared to standard ECG signals. The ECG signal includes one full heartbeat, represented as a collection of critical points in the ECG. By noting certain intervals and comparing them to standard readings, these PQRST points are utilized to identify ECG irregularities or arrhythmias. One of the features of the device is to display the reading of the electrocardiogram on the computer screen with extreme accuracy, and this benefits the specialist doctor during the diagnosis. In addition, three electrodes were used instead of the 12 electrodes normally used. [ABSTRACT FROM AUTHOR]

Arrhythmia is an abnormality in the rhythm of the heartbeat. The detection of cardiac arrhythmia in minimal time is important to prevent sudden deaths. Cardiologists use Electrocardiogram (ECG) to detect such abnormalities in the rhythm of the heartbeat. Deep Learning is one of the emerging technologies in classification. We can use deep learning to detect and classify ECG, which plays an essential role in patient monitoring. This paper gives a detailed review of the recent deep learning methods used in ECG for classification. This paper also discusses various deep learning methods such as Convolutional Neural Network (CNN), Deep Belief Network (DBN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Generative Adversarial Networks (GANs). Among these methods, Convolutional Neural Network is the most suitable method for feature extraction. Classifications based on Deep learning methods are known to be highly accurate. [ABSTRACT FROM AUTHOR]

Research related to the use of the UCI repository arrhythmia dataset has been widely carried out. They classify the dataset to produce accuracy values in the proposed model. However, the problem of missing value in the dataset and imbalance learning in the class dataset are not the focus of the discussion. At the initial stage, the dataset will undergo data preprocessing to get free data and no missing values. The dataset will be processed into 2 parts for training data of 70% and testing data of 30%. In the training data, we also do feature selection with Particle Swarm Optimization. The result of selection features generated from Particle Swarm Optimization, we apply to data testing. The validation test used is K-Fold Cross Validation with K-Nearest Neighbors classification algorithm, Regression Logistic, SVM Linear, SVM Kernel and Neural Network Multilayer Perceptron which will produce a prediction model. The preprocessing process by replacing missing values and class imbalance learning applied to the arrhythmia dataset sourced from the UCI Repository produces better data completeness and provides accurate validation of results. The labels on the dataset class also become balanced after going through this process. For comparison of recall values on testing data, KNN model, Logistic regression and Linear SVM after undergoing feature selection using PSO the recall value becomes better. Logistic regression model experienced the highest increase of 17.78%. In general, feature selection using PSO has a fairly good impact on increasing recall values in models that have been applied to arrhythmia classification. [ABSTRACT FROM AUTHOR]

Human heart beats between 60 and 100 times in a minute, if more than that means the heart is experiencing an abnormal beat. An abnormal heartbeat is called arrhythmia. The purpose of this study is to detect heart rate through photoplethysmograph signals and the patient's position can be known using the global position system (GPS) on the georaphic information system (GIS). Photoplethysmograph which is used for monitoring heart rate by looking at changes in blood volume in blood vessels. The heart rate test from the pulse sensor is processed at the ADC in the microcontroller, and heart rate data is sent via bluethoot media to the patient's cell phone, with the mobile telecardiac system the data can be seen by doctors or nurses and ambulance units. In the simulation of the tool, samples of heart rate data were taken from 10 normal people. The average sensor output voltage value is 0.437 volts with an average heart rate of 72 bpm. Patients with heart rate arrhythmias can be divided into 2 types, namely bradycardia (small 60 bpm) and tachycardia (greater than 100 bpm). The results of testing the number of detected heartbeats are displayed on the smartphone in the form of a signal. This study provides an arrythmia detector where if the heart rate is less than 60 bpm it includes symptoms of arrhythmia called bradycardia (weak heartbeat), whereas if the heart rate is more than 100 bpm then it is a symptom of arrythmia. Based on the research that has been done, the tool has an average error of 0.87% in reading heart rate. [ABSTRACT FROM AUTHOR]

This paper presents detection of arrhythmia on FPGA kit using ECG signals. The objective is to implement Support Vector Machine (SVM) on FPGA to find anomalies in Electrocardiogram (ECG), with a better accuracy, compared to other statistical methods. The methodology focuses on filtering the baseline wander noise as residue that is already embedded in the ECG signal that is given as input to the system using FIR filter. Feature selection is done by Discrete Wavelet Transform (DWT). The feature set from the ECG signal is given as input to the classifier which classifies the signal using the SVM technique. MIT-BIH Arrhythmia database has been used for the input signals. A classification accuracy of 99.4% was achieved for this database. FPGA board is used to implement this whole system using the principles and codes of Xilinx and MATLAB. [ABSTRACT FROM AUTHOR]

The human heart beats rhythmically, maintaining a steady beat to pump blood across the body. This constant beating is also required to maintain the vessel blood pressure, preventing circulatory collapse and subsequently ischemia or infarction. Arrhythmia or irregular rhythm, due to a pre-existing condition or damage to the heart's neuromuscular structure, can lead to a change in the heart rate and the flow pressure in the blood vessels. In resolvable or temporary arrhythmia, the therapeutic procedure of choice remains synchronized cardioversion. Cardioversion, a procedure akin to defibrillation, essentially involves reconfiguring the heart's electrical system by delivering a calculated charge of electric current at the appropriate junction in the cardiac rhythm. However, if performed unnecessarily or incorrectly, cardioversion can result in arrhythmia or cardiac arrest. Thus in cases requiring the utilization of this protocol, it is of vital importance to monitor the patient's cardiac rhythm and deliver the cardioversive shock only at the appropriate juncture. This paper reviews the various techniques utilized to track and deliver cardioversion. [ABSTRACT FROM AUTHOR]

Modern biomedical equipment can be immune to various types of noise, but not to basiс noise and power disturbances. These noise sources have frequency spectra that contaminate the corresponding electrocardiogram (ECG) spectra. The digital signal processing algorithms in the preprocessing modules of electrocardiographic apparatus play a key role in providing high quality ECG signals for analysis, interpretation and presentation. Due to the overlap of the signal and noise power spectrum in received ECG data, in frequency selective filters there is a problem between noise removal and the possible deformation of the useful signal. Most importantly, the filtering result should not adversely affect subsequent diagnosis and interpretation. This work carried out a quantitative study of results evaluation between the Remez and Chebyshev filters based on the minimum root-mean-square error, a higher signal-to-noise ratio and peak signal-to-noise ratio in a Python environment using a notch filter. The results showed that the noise signal using the Remez filter has a better balance between smoothness and accuracy than the Chebyshev filter. However, the Chebyshev filter has a minimal computational load and can be used in microcomputer-based arrhythmia monitors. [ABSTRACT FROM AUTHOR]

In medical science, ECG signal analysis is one of the primary criteria for detecting cardiovascular diseases. ECG possesses morphological properties P-QRS-T, and many heart disorders may be detected by studying the variance in these properties. The existence of different disturbances in ECG signals has a major influence on feature extraction, and clinicians are unable to detect clinical features for diagnosis due to the presence of noise. Therefore, we have introduced a new ECG signal denoising scheme where we have proposed an optimized threshold function in discrete Wavelet transform(DWT) domain by utilizing the characteristics of rigresure, and Sqtwolog which provides relatively better results unlike traditional threshold functions in conjunction with DWT. Based on experimental findings, a comparative analysis of different state-of-the-art methods has been made on well-known MIT-BIH arrhythmia database and found, our proposed method outperformed in terms of signal to noise ratio (SNR) which ranges from 47.37 to 54.27, lower root mean square error(RMSE) ranges from 0.0007 to 0.0037 and relatively lower percentage root mean square difference PRD which ranges from 0.144 to 0.456 respectively. [ABSTRACT FROM AUTHOR]

The study aims to develop machine-learning models to predict cardiac adverse events in female breast cancer patients who receive adjuvant therapy. We selected breast cancer patients from a retrospective dataset of the Taipei Medical University Clinical Research Database and Taiwan Cancer Registry between January 2004 and December 2020. Patients were monitored at the date of prescribed chemo- and/or -target therapies until cardiac adverse events occurred during a year. Variables were used, including demographics, comorbidities, medications, and lab values. Logistics regression (LR) and artificial neural network (ANN) were used. The performance of the algorithms was measured by the area under the receiver operating characteristic curve (AUC). In total, 1321 patients (an equal 15039 visits) were included. The best performance of the artificial neural network (ANN) model was achieved with the AUC, precision, recall, and F1-score of 0.89, 0.14, 0.82, and 0.2, respectively. The most important features were a pre-existing cardiac disease, tumor size, estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), cancer stage, and age at index date. Further research is necessary to determine the feasibility of applying the algorithm in the clinical setting and explore whether this tool could improve care and outcomes. [ABSTRACT FROM AUTHOR]

It is well established that HCQ has anti-inflammatory and immunosuppressive, but it has stopped as treatment for Covid-19 because it affect increase heart rhythm. So this research aimed to demonstrate the effect of HCQ treatment on concentrations of plasma TNF-α and IL-6 in.mice and its relationship with glucocorticoids level which could explain the arrhythmias. In this research, 30 adult male Balb/C mice were used. The mice aged 2-3months were divided into 3groups; one treated with high-dosage of HCQ (8.1mg/kg body-weight, twice for 10days); second with low-dosage (6.4mg/kg body-weight, twice on one day and once on other 4days); and third was left without treatment to be serve as a control group. At different points time, the mice were sacrificed by cervical distraction. A blood sample is taken from the eye and the serum is separated to determine cortisol level by cobas e411 analyzers. Brain, spleen, and kidney were taken and homogenized. Aliquot and serum were be used to determine TNF-α and IL-6 level by sandwich ELISA using murine IL-6 and TNF-α kits (Melsin/China). The results showed a significantly lower cortisol, IL-6, and TNF-α level in serum and tissues of both treated groups compared to control. The reduction of cytokines are believed to inhibit the HPA axis resulting in decrease glucocorticoids level which could be good prove of the interplay between immune and endocrine systems. So it is very important to check cortisol level during HCQ treatment and it is preferred to use a combined treatment between HCQ and glucocorticoid. [ABSTRACT FROM AUTHOR]

The usage of a Back Spread Neural Network for ECG waveform classification utilizing discrete wavelet change was the focus of this paper. We have been picked of MIT-BIH arrhythmia database and got 45 archives out of 48 reports of brief narrative where 25 records are considered as would be normal class and 20 archives of strange taking into account Maximum number of beats present in each record. BPNN was used to organize ECG sensor readings for unnatural classification. The characteristics are divided into two categories: DWT-based characteristics and morphology ECG signal characteristics that serve as a commitment to classification. The ECG data was organized using a Back Propagation Neural Network and the structure execution was evaluated based on rate correctness. For the Strange model 100% of accuracy is come to while 96% of precision was cultivated for normal ECG test. The all things considered structure accuracy 97.8 % was procured with the usage of BPNN classifier. This paper handles with the clatter ejection of ECG signal using three particular wave families. The different commotion structure (unsealed clamor, scaled commotion and nonwhite clamor) are hand-picked for ECG flags and contrasted their factual parameter with mapped out the least complex outcome. [ABSTRACT FROM AUTHOR]

During surgery under anesthesia in dogs with neurological deficits, dangerous arrhythmias can occur, which can lead to a decrease in cardiac output, impaired coronary blood flow and pumping function. The main causes of arrhythmias are: hypoxia, electrolyte and acid-base disturbances, changes in the activity of the autonomic nervous system, hypertension, hypotension, anesthetics, hypothermia, surgical stimulation, reflex provocation of arrhythmias during intubation, concomitant diseases of the heart and its conducting system. Mandatory pre-anesthetic electrocardiological and echocardiographic studies, continuous intraoperative cardiac monitoring, taking into account the factors of arrhythmias and criteria for an indicator of an increased risk of the transition of clinically significant or fatal arrhythmias, will increase the likelihood of successful anesthesia. When carrying out anesthesia, acute arrhythmias that cause clinical signs of hemodynamic disturbance must be eliminated. [ABSTRACT FROM AUTHOR]

Arrhythmia is a disease characterized by abnormal conductivity within the heart that ends up in ineffective pumping. Dysfunctional nodes within the conductivity pathway or within the internal organ muscles cause irregular heartbeat patterns which will probably induce severe complications like cardiopulmonary arrest. This paper discusses the different method of previous writing for separating highlight from an Arrhythmia review and study of Electrocardiogram (ECG) signal. Classification of ECG signal is one of the most significant reasons for diagnosing the heart diseases. There are many types of classifiers available for ECG classification. An ECG is a test that records the electrical activity of the heart to find the anomalies. The programmed ECG arrangement is a rising device for the cardiologists in medicinal finding for compelling medications. ECG investigation has been set up as a key component with respect to the assessment of human wellbeing status. In this investigation, we analyze various techniques available in ECG signal during heart diseases. [ABSTRACT FROM AUTHOR]

Electrocardiography (ECG) is an essential non-invasive tool for classification and diagnosing a cardiac arrhythmia. Many methods using ECG signals for the classification of different types or classes of heartbeats are proposed. These classes are started from normal beats or abnormal beats and reached many types based on the classification methods and the variability of database beat types. A low computation method with high accuracy is a challenge for many researchers in this field that can be implemented in a real-time monitoring system. The proposed classification algorithm is a low-computation, real-time, and high-performance technique based on artificial neural networks (ANN). In this work, the three stages algorithm is designed and evaluated for low computation applications. The first stage is filtering the original ECG signal, features extraction for QRS, and QRS-detection. In the second stage, the new features are extracted from RR- interval and added to the same QRS-detection features. Finally, A simple ANN is designed to classify the beats for two classes (normal and abnormal) based on the QRS shape used for detection and the RR-interval features. The algorithm is evaluated using MIT-BIH Arrhythmia Database and MATLAB software. The accuracy of 98.97%, recall of 99.42%, and high precision of 99.13% are promising results for a low computation algorithm. It is a new approach for real-time applications with low resources and high efficiency compared with the other classifier approaches. [ABSTRACT FROM AUTHOR]

This paper focuses on the development of a low-cost electrocardiographic device for the timely detection of cardiac arrhythmias such as tachycardia and bradycardia; disorders that can occur sporadically in a person's daily life. The architecture of the system for the classification of electrocardiogram (ECG) beats is based on a deep learning approach developed in Python 3 with low-cost and open-source elements. The training of the network is based on the background of the MIT-BIH database based on the AAMI and focused on 5 categories of cardiac beats of patients. The 1D convolutional neural network model was trained and validated using the TensorFlow and Keras libraries with an efficiency of 98%. The convolutional network tests are continuously monitored in real time in order to present the patient with the appropriate diagnosis or treatment. In case of any abnormality, an alert message is sent to the physician via a mobile application. [ABSTRACT FROM AUTHOR]

Atrial fibrillation (AF) is a widespread heart disease which prevalence increases essentially in the elderly. In this study, we combined age-related changes in cardiomyocytes electrophysiology with the effects of chronic atrial fibrillation on the population of human atrial cell models. Our age-dependent populations of models are able to reproduce experimentally observed effects of aging on action potential (AP) and calcium transient (CaT) morphology. Simulation of AF remodeling in aging models allowed us to reproduce specific shortening of AP duration on a 90% level, an increase in AP plateau, and a reduction in CaT amplitude. Our modeling results predict the increased risk of sustained arrhythmia in the elderly group of models. [ABSTRACT FROM AUTHOR]

Detection of the heart rate disturbances is one of the main functions of the ECG monitoring systems. Atrial fibrillation represents one of the most dangerous and widespread cardiac arrhythmias that may cause development of apoplexy and even lead to the patient's death. Many algorithms for detection of this decease with the use of ECG analysis are proposed by now, but the best of them demonstrate accuracy of atrial fibrillation detection no more than about 94.5 %. This paper is devoted to the new method of this arrhythmia detection showing high level of specificity that permit to avoid the decease hyper diagnostics. [ABSTRACT FROM AUTHOR]

The heart muscle activity monitoring and possibility of timely detection of its pathologies are considered as important tasks of modern medicine since cardiovascular deceases represent the most common cause of human death. This paper is devoted to the development of neural network based algorithm for the binary classification of the ECG cardiac beats waveforms into the following two categories: background beats and the beats with considerably deviated forms. The vector transformation of the signal was used as a method of the ECG representation where synchronous values of ECG signal from different leads were interpreted as the vector coordinates. Three variants of the vector transformation were examined in order to check the robustness of the waveform classification procedure to the possible loss of some signal features: with the use of one, two and three ECG leads. Before the classification procedure, the ECG signals were preprocessed using digital filtering and spline interpolation. The feedforward neural network structure with one hidden layer was used for the waveforms classification. Some standard methods to avoid the network overfitting were applied. The results of the proposed algorithm testing showed rather good values of its accuracy estimates. As it was expected, the best results were obtained when all three synchronous ECG leads were used. Thus, the presented in this paper approach can be used as a base for the further development of a noise robust cardiac arrhythmia detection algorithm. [ABSTRACT FROM AUTHOR]

A multi-parametric algorithm for the premature ventricular contractions detection based on both heart rhythm and ECG shape alternations is proposed. Six different QRS shape metrics are tested and their weighted combination is used to suggest an aggregated shape parameter. In the multi-lead ECG analysis each lead is weighted proportionally to its individual signal-to-noise ratio. Our results indicate that the proposed combined algorithm outperforms several complementary metrics in PVCs detection accuracy yielding ultimate performance characterized by Se=82.70, Sp=98.82 and +P=82.97 for the 2-lead MIT-BIH Arrhythmia Database as well as Se=92.87, Sp=99.64 and +P=97.03 for the St. Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database. [ABSTRACT FROM AUTHOR]

The method of phase space reconstruction by the time characteristics of biomedical signals is described. It is shown that the Poincaré plot contains useful information related to the presence of nonlinear components in the process under study. The method of analyzing a sequence of ECG cardiocycles is proposed in order to diagnose several types of arrhythmias. During experiments on a sample of real ECG signals, it was established, that the Poincaré mapping allows one to obtain additional information on the dynamics of the behavior of the time series and, due to this, it is more efficient to solve the problems of classifying states in health and pathology. [ABSTRACT FROM AUTHOR]

Cardiac arrhythmias still are among the major causes of morbidity and death around the world and in Mexico too. Reentry is one of the most prevalent tachycardia. Anatomical reentry strongly depends on the surrounding tissue characteristics, in this paper, we use a previously tested in vitro reentry model from embryonic ventricular cardiomyocytes to analyze the recovery effect of hypothermia. We found that mild and moderate hypothermia, induce changes in intracellular calcium activity along the cardiomyocytes cell ring evolving from a sustained reentry to a stable pacemaker. Recurrent plots are very sensitive to reveal swift local transitions occurring precisely before the tachycardia extinction. [ABSTRACT FROM AUTHOR]

Automatic classification of electrocardiogram (ECG) is importance in cardiac disease diagnosis. Support vector machine (SVM) has drawn more and more attention on pattern recognition, including ECG feature extraction and cardiac disease detection. The most prominent advantage of SVM can be represent as its excellent performance on simplification of inner product operation from high dimensional space to low dimensional space, avoiding calculations in high dimension space. In this study, a multi-classification method is proposed utilizing wavelet multi-resolution analysis (WMRA) and SVM. WMRA is applied to eliminate interference with frequency beyond the frequency interval of ECG signals (0.05~100Hz). Meanwhile, WMRA provides detail coefficients and approximation coefficients of different decomposition levels, which are the input features fed into SVM for classification. After that, SVM is employed to recognize 6 types of cardiac beats from MIT-BIH arrhythmia database. Besides, different parameters C and γ are discussed and tested. Experimental results indicate that the classification performance gets better as C increases and γ decreases. When C and γ are set to be 1000 and 0.1 respectively, an overall classification accuracy, sensitivity and positive predictivity of 95.23%, 97.42% and 97.71% respectively are achieved. [ABSTRACT FROM AUTHOR]

When dealing with electrocardiography (ECG) the main focus relies on the classification of the heart’s electric activity and deep learning has been proving its value over the years classifying the heartbeats, exhibiting great performance when doing so. Following these assumptions, we propose a deep learning model based on a ResNet architecture with convolutional 1D layers to classify the beats into one of the 4 classes: normal, atrial premature contraction, premature ventricular contraction and others. Experimental results with MIT-BIH Arrhythmia Database confirmed that the model is able to perform well, obtaining an accuracy of 96% when using stochastic gradient descent (SGD) and 83% when using adaptive moment estimation (Adam), SGD also obtained F1-scores over 90% for the four classes proposed. A larger dataset was created and tested as unforeseen data for the trained model, proving that new tests should be done to improve the accuracy of it. [ABSTRACT FROM AUTHOR]

The aim of this study is to propose a method to measure QT interval of electrocardiogram (ECG). Firstly, in this proposed QT interval measurement, the P-wave and QRS complex of ECG signal is removed to detect the T end. Then, the ECG signal is passed through differentiated process. T end is defined as point where last maximum or minimum differentiated signal reaches the threshold value. Threshold value is variated with 5% (TH1), 10% (TH2), and 50% (TH3) of last maximum or minimum value of differentiated signal. The proposed method is compared to reference measurement that provided by Physionet QT Database. The proposed algorithm has been evaluated using clinical data which is 10 ECG records in the Physionet QT Database. Mean difference of proposed QT interval measurement and reference QT interval measurement are 15.4 ± 25.7 ms for TH1, 18.1 ± 25.7 ms for TH2, and 38.2 ± 25.6 ms for TH3. [ABSTRACT FROM AUTHOR]

In this research, an algorithm based on dynamic neural networks was designed to pre-diagnose cardiac diseases. The neural network learns from a database of signals with cardiac conditions (arrhythmias) and through real-time monitoring, the patterns are searched to identify whether the test subject is healthy or suffers of heart disease. The dynamic neural network functions as an estimator of states, through time, it learns the dynamics of the cardiac suffering signal, assimilating its behavior. Applying the mean square error, we can compare them and know if they are identical. Signals of interest are under a pre-define analysis and through their variations, information from it can be extracted. [ABSTRACT FROM AUTHOR]

Copyright of Proceedings of the International Scientific Conference of Daugavpils University / Daugavpils Universitates Starptautiskas Zinatniskas Konferences Materiali is the property of Daugavpils University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Backgound: The kidney is an essential organ in regulating the electrolyte balance. With the progression to advanced renal insufficiency, disturbances occur, with frequent increases in the level of potassium, which lead to a significant increase in morbidity and mortality in this group of patients, most commonly by cardiovascular complications - arrhythmias and sudden death. Since chronic renal failure has become a global problem and is frequently under-diagnosed, it is very important to have a correct diagnosis and appropriate rapid treatment to reduce the risks associated with hyperkalemia. Aim of study was to review of the pathophysiological processes of electrolytic disturbances involved in renal function disorders as well as diagnosis and treatment strategies. Material and methods: We report the case of a 76 years old Caucasian female, known with severe hypertension, atrial fibrillation, cardiac insufficiency class II NYHA, previous chronic kidney disease, and diabetes mellitus, which came to the hospital for fever, dyspnea with orthopnea and cough. The patient had in her chronic treatment the association between ACE inhibitor and antialdosteronic diuretic. She also took in the last 5 days prior to the admission high amount of NSAIDs. The serum potassium of the patient was 8.6 mEq/L and suddenly cardiovascular complications changed the prognosis of this patient. The final outcome was good because of the fast reaction of the medical team. Conclusions: Although electrolyte disorders occurring in chronic renal failure quickly lead to lifethreatening complications, they can be combated by a series of preventive measures and appropriate treatment. Recent published studies bring important new information about the treatment of this group of pathologies to improve the prognosis of these patients. [ABSTRACT FROM AUTHOR]